This is a complete, runnable project for predicting 10-year risk of coronary heart disease (CHD).
data/raw/framingham.csv- placeholder sample file (replace with full dataset)src/- preprocessing, training and utility codemodels/- trained model and preprocessing pipeline will be saved here after trainingapp/- Streamlit app for interactive predictions
- Install requirements:
pip install -r requirements.txt
- (Optional) Replace
data/raw/framingham.csvwith the original Framingham dataset CSV. - Train the model (this will save
models/best_model.pklandmodels/pipeline.pkl):python3 src/main.py
- Run the Streamlit app:
streamlit run app/streamlit_app.py
- The preprocessing pipeline is saved so the Streamlit app can reliably transform user input.
- The sample CSV included is small and only for structure—replace with the real framingham.csv for meaningful results.